Advanced search
1 file | 465.74 KB

Activation detection in event-related FMRI through clustering of wavelet distributions

Geert Verdoolaege (UGent) and Yves Rosseel (UGent)
Author
Organization
Abstract
We propose a new method for the detection of activated voxels in event-related BOLD fMRI data. We model the statistics of the wavelet histograms derived from each voxel time series independently through a generalized Gaussian distribution (GGD). We perform k-means clustering of the GGDs characterizing the voxel data in a synthetic data set, using the symmetrized Kullback-Leibler divergence (KLD) as a similarity measure. We compare our technique with GLM modeling and with another clustering method for activation detection that directly uses the wavelet coefficients as features. Our method is shown to be considerably more stable against realistic hemodynamic variability.
Keywords
k-means clustering, fMRI, generalized Gaussian distribution, Kullback-Leibler divergence

Downloads

  • verdoolaege.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 465.74 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Verdoolaege, Geert, and Yves Rosseel. 2010. “Activation Detection in Event-related FMRI Through Clustering of Wavelet Distributions.” In IEEE International Conference on Image Processing ICIP, 4393–4396. New York, NY, USA: IEEE.
APA
Verdoolaege, Geert, & Rosseel, Y. (2010). Activation detection in event-related FMRI through clustering of wavelet distributions. IEEE International Conference on Image Processing ICIP (pp. 4393–4396). Presented at the IEEE International conference on Image Processing, New York, NY, USA: IEEE.
Vancouver
1.
Verdoolaege G, Rosseel Y. Activation detection in event-related FMRI through clustering of wavelet distributions. IEEE International Conference on Image Processing ICIP. New York, NY, USA: IEEE; 2010. p. 4393–6.
MLA
Verdoolaege, Geert, and Yves Rosseel. “Activation Detection in Event-related FMRI Through Clustering of Wavelet Distributions.” IEEE International Conference on Image Processing ICIP. New York, NY, USA: IEEE, 2010. 4393–4396. Print.
@inproceedings{1234913,
  abstract     = {We propose a new method for the detection of activated voxels in event-related BOLD fMRI data. We model the statistics of the wavelet histograms derived from each voxel time series independently through a generalized Gaussian distribution (GGD). We perform k-means clustering of the GGDs characterizing the voxel data in a synthetic data set, using the symmetrized Kullback-Leibler divergence (KLD) as a similarity measure. We compare our technique with GLM modeling and with another clustering method for activation detection that directly uses the wavelet coefficients as features. Our method is shown to be considerably more stable against realistic hemodynamic variability.},
  author       = {Verdoolaege, Geert and Rosseel, Yves},
  booktitle    = {IEEE International Conference on Image Processing ICIP},
  isbn         = {9781424479948},
  issn         = {1522-4880},
  keyword      = {k-means clustering,fMRI,generalized Gaussian distribution,Kullback-Leibler divergence},
  language     = {eng},
  location     = {Hong Kong, PR China},
  pages        = {4393--4396},
  publisher    = {IEEE},
  title        = {Activation detection in event-related FMRI through clustering of wavelet distributions},
  url          = {http://dx.doi.org/10.1109/ICIP.2010.5653367},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: